No full-text available
To read the full-text of this research,
you can request a copy directly from the authors.
CPA Calculation Method based on AIS Position Prediction
Abstract
The information on the Closest Point of Approach (CPA) of another vessel to own ship is required in a potential collision situation as it helps determines the risk to each vessel. CPA is usually calculated based on the speed and direction of the approaching ship neglecting the Change Of Speed (COS) and the Rate Of Turn (ROT). This will make the CPA less useful. To improve the CPA calculation, Automatic Identification System (AIS) information containing the Speed Over Ground (SOG), Course Over Ground (COG), COS and ROT is used. Firstly, a model using these four factors is built to predict ship positions better. Secondly, a three-step CPA searching method is developed. The developed CPA calculation method can assist in informing the navigation decisions and reducing unnecessary manoeuvres. Through the analysis of a real collision scenario, this paper shows that the proposed method can help identify and warn of anomalous ship behaviours in a realistic time frame.
... The Closest Point of Approach (CPA) represents a critical navigational metric, estimated as the point where the distance between a vessel and another object-such as another ship or a waterway structure-should be within minimum value [95]. It encompasses two key parameters: the Distance Closest Point of Approach (DCPA) and the Time Closest Point of Approach (TCPA) as shown in Figure 6. ...
... An impact risk is considered to be present when the DCPA is less than a predetermined safe distance, and the TCPA is positive, indicating an impending close approach [93]. CPA was originally introduced when radar was first used to avoid collision [95], the accurate calculation of CPA is useful in maritime navigation for real-time collision avoidance. Figure 6: DCPA and TCPA in the ship-ship collision situation, redrawn from [96] Initially, CPA calculations just considered a vessel's SOG and COG, while ignoring other influential parameters [95]. ...
... CPA was originally introduced when radar was first used to avoid collision [95], the accurate calculation of CPA is useful in maritime navigation for real-time collision avoidance. Figure 6: DCPA and TCPA in the ship-ship collision situation, redrawn from [96] Initially, CPA calculations just considered a vessel's SOG and COG, while ignoring other influential parameters [95]. To address this, more dynamic CPA methods have been developed, incorporating additional parameters. ...
The collisions between bridges and ships might cause severe damage to both of them, which is impossible to avoid completely, although several specifications or requirements need to be followed in the design of bridges and during the navigation of ships passing bridge. Many researches on protective technology had been conducted to reduce the potentially disastrous consequences. These technologies can be broadly categorized into two main types: the technologies of collision avoidance, which try to reduce the collision possibility by warning the passing ship that might impact the bridge; and passive collision protections, which use protective structures to minimize the damage of bridge and ship due to impact. The purpose of the present paper is to systematically summarize both classifications and then provide insights into their characteristics, advantages, disadvantages, and suitable conditions for application. Additionally, the related approaches originally designed for other applications but with potential relevance are also discussed, such as ship-ship collision avoidance. This review can serve as meaningful guidance and reference for future research and realistic engineering applications.
... The calculation of the distance of the CPA requires complex procedures and formulas, which have already been reported in various references [33,34]. Using the formulas in [35], dCPA(t) was calculated using the following procedure: ...
... Distance measures ( , ) or ( , ) between models and have a dissimilarity concept with respect to model distance. Several interpretations of the model distance exist in terms of such as cross entropy, divergence, and discrimination of information [28,35]. The is a measure result of how well the model matches observations generated by model , relative to how well model matches observations generated by itself. ...
... Distance measures D(λ Fail , λ Success ) or D(λ Success , λ Fail ) between models λ Fail and λ Success have a dissimilarity concept with respect to model distance. Several interpretations of the model distance exist in terms of such as cross entropy, divergence, and discrimination of information [28,35]. The MD Success is a measure result of how well the model λ Fail matches observations generated by model λ Success , relative to how well model λ Success matches observations generated by itself. ...
In order to prevent ship collisions, it is important to understand the behavior of navigators that leads to these collisions. The main cause of marine accidents in the Republic of Korea is attributed to navigator error, particularly in collisions. Hence, reducing navigator error is a key issue that needs to be addressed to prevent accidents. However, the lack of objective measure to quantify navigator error remains a challenge. The purpose of this study is to develop an objective identification of a navigator’s behavior in a collision encountering situation. Two behavior models for the success and failure of collision avoidance are developed by collecting participants’ actions, using a ship maneuvering simulator within a given scenario. These maneuvering behavior models are validated in terms of their discrimination powers. The results show that maneuvering behavior is clearly identified in the data processing and model development phases. The proposed behavior models are expected to provide a better understanding of how navigators behave to help reduce collision accidents.
... The first is to cluster all historical trajectories, design cluster classifiers, and train their own local behavior network for each cluster [2], [18]. The second is to extract the typical waterway and use it to correct the prediction results of the neural network [12], [19], [20]. From a higher dimensional perspective, these methods use preexisting or extracted knowledge to assist neural networks in predicting trajectories. ...
... There are methods that use neural networks to predict the sog and cog of a vessel, and then obtain its latitude and longitude by building a motion physics model [12], [19]. The MSTFomer uses ∆sog, ∆cog for prediction, and the data series after performing differencing is more stationary, which is beneficial to improve the prediction accuracy. ...
Incorporating the dynamics knowledge into the model is critical for achieving accurate trajectory prediction while considering the spatial and temporal characteristics of the vessel. However, existing methods rarely consider the underlying dynamics knowledge and directly use machine learning algorithms to predict the trajectories. Intuitively, the vessel's motions are following the laws of dynamics, e.g., the speed of a vessel decreases when turning a corner. Yet, it is challenging to combine dynamic knowledge and neural networks due to their inherent heterogeneity. Against this background, we propose MSTFormer, a motion inspired vessel trajectory prediction method based on Transformer. The contribution of this work is threefold. First, we design a data augmentation method to describe the spatial features and motion features of the trajectory. Second, we propose a Multi-headed Dynamic-aware Self-attention mechanism to focus on trajectory points with frequent motion transformations. Finally, we construct a knowledge-inspired loss function to further boost the performance of the model. Experimental results on real-world datasets show that our strategy not only effectively improves long-term predictive capability but also outperforms backbones on cornering data.The ablation analysis further confirms the efficacy of the proposed method. To the best of our knowledge, MSTFormer is the first neural network model for trajectory prediction fused with vessel motion dynamics, providing a worthwhile direction for future research.The source code is available at https://github.com/simple316/MSTFormer.
... Second, CAMs must be distinguished from normal routefollowing and track-keeping actions imposed by traffic separation schemes and natural obstacles. The proposed framework uses speed and course patterns, as well as vessel position, to incorporate the closest point of approach (CPA) algorithm, as described by Sang et al. (2016). This determines an estimated time to CPA and an estimated distance at CPA for every vessel at every timestamp. ...
... The following discusses the identification of real NCSs for an NCS database based on historical traffic data from AIS. The CPA framework is established by Sang et al. (2016) as a method for analysing the collision behaviour of two objects in motion. CPA is defined as the closest point two objects will arrive at if speed and course are unaltered. ...
Economic and technological development has increased the amount, density and complexity of maritime traffic, which has resulted in new challenges. One challenge is conforming to the distinct evasion manoeuvres required by vessels entering into near-collision situations (NCSs). Existing rules are vague and do not precisely dictate which, when and how collision avoidance manoeuvres (CAMs) should be executed. The automatic identification system (AIS) is widely used for vessel monitoring and traffic control. This paper presents an efficient, scalable method for processing large-scale raw AIS data using the closest point of approach (CPA) framework. NCSs are identified to create a database of historical traffic data. Important features describing CAMs are defined, estimated and analysed. Applications on a high-quality real-world data set show promising results for a subset of the identified situations. Future applications may play a significant role in the maritime regulatory framework, navigation protocol compliance evaluation, risk assessment, automatic collision avoidance, and algorithm design and testing for autonomous vessels.
... These methods need to perceive all risky situations in their first stage which is very important for navigation safety. Risk identification was considered in Reference [16] based on Automatic Identification System (AIS) data and the Closest Point of Approach (CPA) [17] as well as distance at CPA and time to CPA parameters. These are typically based on assumptions of linear tracks, constant speed and course and neglect vessel dimensions and maneuverability. ...
... The longitudinal, lateral and spatial risk functions for collision and grounding, respectively, are shown in Figure 7. Notice that the same vessel domain ( Figure 5) and risk evaluation parameters Equation (6) are used for collision and grounding risk evaluation, however, with different spatial functions (Equations (16) and (17) and Figure 7). The main advantage here is to ensure memory-efficiency such that each AIS message in combination with vessel dimensions is mapped into 14 single-precision floating-point numbers (vertices' x-y coordinates defined by Equation (11) and four parameters of Equation (6)). ...
The continuous growth in maritime traffic and recent developments towards autonomous navigation have directed increasing attention to navigational safety in which new tools are required to identify real-time risk and complex navigation situations. These tools are of paramount importance to avoid potentially disastrous consequences of accidents and promote safe navigation at sea. In this study, an adaptive ship-safety-domain is proposed with spatial risk functions to identify both collision and grounding risk based on motion and maneuverability conditions for all vessels. The algorithm is designed and validated through extensive amounts of Automatic Identification System (AIS) data for decision support over a large area, while the integration of the algorithm with other navigational systems will increase effectiveness and ensure reliability. Since a successful evacuation of a potential vessel-to-vessel collision, or a vessel grounding situation, is highly dependent on the nearby maneuvering limitations and other possible accident situations, multi-vessel collision and grounding risk is considered in this work to identify real-time risk. The presented algorithm utilizes and exploits dynamic AIS information, vessel registry and high-resolution maps and it is robust to inaccuracies of position, course and speed over ground records. The computation-efficient algorithm allows for real-time situation risk identification at a large-scale monitored map up to country level and up to several years of operation with a very high accuracy.
... Exponential smoothing model [174] can be viewed as a statistical machine learning method, which is capable of predicting the periodic time series data. Sang et al. applied the triple exponential smoothing model [175] to predict a vessel's future COG and SOG values; then, the predicted COG and SOG values serve as the input for computing the vessel's positions based on the navigation relationship of position and the COG and SOG states (as well as the Change of Speed (COS) and Rate of Turn (ROT) that can be derived from the successive COG and SOG values) to predict the vessel's future trajectory [176]. Likewise, we summarize the two-step process of the forecasting approach proposed in this work in Fig. 20. ...
... The relationship of any two successive positions[176]. a list of future COG and SOG values can be obtained at sequential future timestamps (It is worth mentioning that the timestamps are discretized with uniform time interval, such as the input COG and SOG values at t-1 and t or the(m −1) th and m th predicted values indicate they are successive values before and after a fixed time interval). The output of the exponential smoothing model is a sequence of COG and SOG values denoted by [c 1 , c 2 , c 3 , . . . ...
Maritime traffic service networks and information systems play a vital role in maritime traffic safety management. The data collected from the maritime traffic networks are essential for the perception of traffic dynamics and predictive traffic regulation. This paper is devoted to surveying the key processing components in maritime traffic networks. Specifically, the latest progress on maritime traffic data mining technologies for maritime traffic pattern extraction and the recent effort on vessels' motion forecasting for better situation awareness are reviewed. Through the review, we highlight that the traffic pattern knowledge presents valued insights for wide-spectrum domain application purposes, and serves as a prerequisite for the knowledge based forecasting techniques that are growing in popularity. The development of maritime traffic research in pattern mining and traffic forecasting reviewed in this paper affirms the importance of advanced maritime traffic studies and the great potential in maritime traffic safety and intelligence enhancement to accommodate the implementation of the Internet of Things, artificial intelligence technologies, and knowledge engineering and big data computing solution.
... Then, we apply an interpolation method to obtain the ship position at the reference time point. Let [26]. ...
... When an AIS message M i occurred in the interval between the k-th reference time and the k + 1-th reference time, i.e., t k < time(M i ) ≤ t k+1 , the position [lat i , lon i ] of the ship for M i is replaced with the position at time t k+1 , where the position is determined by the interpolation with the motion vector, i.e., course θ and speed v. Let ∆t = t k+1 − time (M i ). The following shows the interpolation equations for the new position at the reference time point [26]. ...
In a crowded harbor water area, it is a major concern to control ship traffic for assuring safety and maximizing the efficiency of port operations. Vessel Traffic Service (VTS) operators pay much attention to caution areas like ship route intersections or traffic congestion area in which there are some risks of ship collision. They want to control the traffic of the caution area at a proper level to lessen risk. Inertial ship movement makes swift changes in direction and speed difficult. It is hence important to predict future traffic of the caution area earlier on so as to get enough time for control actions on ship movements. In the harbor area, VTS stations collect a large volume of Automatic Identification Service (AIS) sensor data, which contain information about ship movement and ship attributes. This paper proposes a new deep neural network model called Ship Traffic Extraction Network (STENet) to predict the medium-term traffic and long-term traffic of the caution area. The STENet model is trained with AIS sensor data. The STENet model is organized into a hierarchical architecture in which the outputs of the movement and contextual feature extraction modules are concatenated and fed into a prediction module. The movement module extracts the features of overall ship movements with a convolutional neural network. The contextual modules consist of five separated fully-connected neural networks, each of which receives an associated attribute. The separation of feature extraction modules at the front phase helps extract the effective features by preventing unrelated attributes from crosstalking. To evaluate the performance of the proposed model, the developed model is applied to a real AIS sensor dataset, which has been collected over two years at a Korean port called Yeosu. In the experiments, four methods have been compared including two new methods: STENet and VGGNet-based models. For the real AIS sensor dataset, the proposed model has shown 50.65% relative performance improvement on average for the medium-term predictions and 57.65% improvement on average for the long-term predictions over the benchmark method, i.e., the SVR-based method.
... In maritime navigational decision support systems, the distance to the closest point of approach (DCPA) and time to the closest point of approach (TCPA) are critical safety parameters used to assist navigators in determining when and how to take collision avoidance measures [42,43]. The DCPA is the closest distance that would be reached if both vessels were to maintain their current speed and course, whereas the TCPA is the time required to reach this closest distance [44]. ...
Vessel trajectory prediction plays a crucial role in ensuring the safety and efficiency of maritime transportation. This study proposes an innovative sequence-to-sequence model, called the Vessel Influence Long Short-Term Memory (VI-LSTM), which introduces a novel Vessel Influence Map (VIM) to quantitatively model the dynamic effects of surrounding vessels. To enhance reliability, VI-LSTM incorporates Gaussian distribution predictions combined with Monte Carlo dropout techniques to estimate prediction uncertainty. Additionally, a temporally weighted hybrid loss function is designed to balance prediction accuracy and uncertainty. Furthermore, this study systematically categorizes and models factors influencing vessel trajectory prediction. Experimental results demonstrate that VI-LSTM achieves a mean distance error of 330.66 m on the standard test set and 480.30 m on an unseen subject test set, outperforming other comparative models, particularly in complex navigation scenarios and high-density maritime environments. These innovations significantly improve the accuracy and generalizability of vessel trajectory predictions, leading to enhanced safety, increased efficiency, and more effective collision avoidance in maritime navigation.
... In recent years, many vessel trajectory prediction studies have been carried out based on AIS data. Earlier, based on traditional mathematical models [5] and physical principles, the basic principles of Newtonian mechanics, nonlinear differential equations, and other methods were applied to model the vessel's trajectory by combining the speed, heading, position and velocity information in the vessel's AIS data, and then the linear interpolation was used to predict the vessel's position [6][7][8][9]. However, these methods usually rely on predefined motion patterns, are less robust to noise and error data in AIS data, lacking the ability to respond flexibly to autonomous vessel behaviours and changes in the external environment, thus limiting their application in dynamic and complex marine environments. ...
Vessel trajectory prediction is important in maritime traffic safety and emergency management. Vessel trajectory prediction using vessel automatic identification system (AIS) data has attracted wide attention. Deep learning techniques have been widely applied to vessel trajectory prediction tasks due to their advantages in fine-grained feature learning and time series modelling. However, most deep learning-based methods use a unified approach for modelling AIS data, ignoring the diversity of AIS data and the impact of noise on prediction performance due to environmental factors. To address this issue, this study introduces a method consisting of temporal convolutional network (TCN), convolutional neural network (CNN) and convolutional long short-term memory (ConvLSTM) to predict vessel trajectories, called TCC. The model employs TCN to capture the complex correlation of the time series, utilises CNN to capture the fine-grained covariate features and then captures the dynamics and complexity of the trajectory sequences through ConvLSTM to predict vessel trajectories. Experiments are conducted on real public datasets, and the results show that the TCC model proposed in this paper outperforms the existing baseline algorithms with high accuracy and robustness in vessel trajectory prediction.
... The earliest ship trajectory prediction methods were based on modeling ship movement characteristics. These models often relied on ideal conditions and were only applicable to some fixed sea areas [8]. With the advancement of machine learning, more machine learning models have been developed for ship trajectory prediction [9]. ...
The analysis of large amounts of vessel trajectory data can facilitate more complex traffic management and route planning, thereby reducing the risk of accidents. The application of deep learning methods in vessel trajectory prediction is becoming more and more widespread; however, due to the complexity of the marine environment, including the influence of geographical environmental factors, weather factors, and real-time traffic conditions, predicting trajectories in less constrained maritime areas is more challenging than in path network conditions. Ship trajectory prediction methods based on kinematic formulas work well in ideal conditions but struggle with real-world complexities. Machine learning methods avoid kinematic formulas but fail to fully leverage complex data due to their simple structure. Deep learning methods, which do not require preset formulas, still face challenges in achieving high-precision and long-term predictions, particularly with complex ship movements and heterogeneous data. This study introduces an innovative model based on the transformer structure to predict the trajectory of a vessel. First, by processing the raw AIS (Automatic Identification System) data, we provide the model with a more efficient input format and data that are both more representative and concise. Secondly, we combine convolutional layers with the transformer structure, using convolutional neural networks to extract local spatiotemporal features in sequences. The encoder and decoder structure of the traditional transformer structure is retained by us. The attention mechanism is used to extract the global spatiotemporal features of sequences. Finally, the model is trained and tested using publicly available AIS data. The prediction results on the field data show that the model can predict trajectories including straight lines and turns under the field data of complex terrain, and in terms of prediction accuracy, our model can reduce the mean squared error by at least 6×10−4 compared with the baseline model.
... Furthermore, the application of an extended Kalman filter [16][17][18] and particle filters [19] was used to enhance the prediction results of the ship dynamic model by incorporating observed position data. Extrapolation [2,14,[20][21][22][23] is a straightforward technique that predicts the future position of a vessel by assuming that the observed state data at the most recent time will remain constant. Ship dynamics models, filter-based models, and extrapolations are appropriate for short-term trajectory prediction that necessitates real-time observations because they do not account for future nonlinear changes in input values. ...
Accurate forecasting of ship encounter positions is crucial for preventing collisions at sea. This paper presents a framework for predicting a ship’s trajectory using a sparse Gaussian process. The proposed method effectively addresses the limitations of existing full Gaussian processes, specifically the significant storage requirements and time complexity associated with data training. The model is trained using Automatic Identification System (AIS) data on trajectories, with hyperparameters optimized through a genetic algorithm. Experimental analysis demonstrates that the proposed model reduces average time complexity by 61.3 s and improves average prediction error to 9.2 m compared to full Gaussian-process-based models.
... One such problem is developing techniques to allow ships to safely interact with each other. Starting from the safe domain concept [Hansen et al. 2013], through Closest Point of Approach (CPA) and Time to Closest Point of Approach (TCPA) as safety indicators [Sang et al. 2016;Li et al. 2021] and ending with analyses of the navigation parameters selected by the Officer on Watch (OOW) [Zhang 2015], the feasibility of these aspects is considered for the safety of navigation. Attempts are being made to establish relatively rigid thresholds to enable safe navigation in both fully-manned and autonomy-intensive maritime traffic. ...
The development of technology has reduced the crews of ships. This trend leads to at least partial elimination of human crews in favour of autonomous ships. As more and more of them will be introduced, a safety problem arises when manoeuvring the ships in relation to each other. Therefore, there is a need to identify the factors that have an impact on determining how to maintain safe distances between ships in order to find relationships that will be useful for the development of autonomous ships. This can currently only be analysed on samples of manned vessels. Therefore, this paper aims to analyse the correlation of the Bow Crossing Range (BCR) with other ship-related data provided by AIS on ships up to 100 m long. The results of this study may be found interesting by academia, maritime industry, and autonomous ship developers.
... The ESM is used to predict the location, course, and speed of the ship; meanwhile, the actual collision scene of the ship is analyzed. This method has been shown to achieve the prediction of ships' behavior [2]. Mazzarella proposed a Bayesian algorithm based on particle filters that uses KNN to match the current trajectory sequence of the ship, enabling the prediction of ship trajectories when traffic route data are available [3]. ...
The extraction of ship behavior patterns from Automatic Identification System (AIS) data and the subsequent prediction of travel routes play crucial roles in mitigating the risk of ship accidents. This study focuses on the Wuhan section of the dendritic river system in the middle reaches of the Yangtze River and the partial reticulated river system in the northern part of the Zhejiang Province as its primary investigation areas. Considering the structure and attributes of AIS data, we introduce a novel algorithm known as the Combination of DBSCAN and DTW (CDDTW) to identify regional navigation characteristics of ships. Subsequently, we develop a real-time ship trajectory prediction model (RSTPM) to facilitate real-time ship trajectory predictions. Experimental tests on two distinct types of river sections are conducted to assess the model’s reliability. The results indicate that the RSTPM exhibits superior prediction accuracy when compared to conventional trajectory prediction models, achieving an approximate 20 m prediction accuracy for ship trajectories on inland waterways. This showcases the advancements made by this model.
... In addition to the above methods, scholars also use other machine learning methods to predict ship trajectories, such as a singlepoint neighbour search method (Murray and Perera, 2022) for ship behaviour prediction, an improved cultural particle swarm method (Zheng et al., 2021) for vessel steering angle prediction, the k-Nearest-Neighbours (k-NN) algorithm (Maskooki et al., 2021) for optimal navigation route selection, a second-order rational Bezier curve coefficients estimation method (Miller and Walczak, 2020), a Bayesian network (Tang et al., 2020) for vessel trajectory prediction, and an improved beetle antennae search algorithm (Xie et al., 2019) for prediction and anti-collision. Furthermore, more advanced methods by the combination of the aforementioned models have also been proposed and applied in ship trajectory prediction, including a K-order Multivariate Markov Chain (KMMC) model , an exponential smoothing model (Sang et al., 2016), an image processing method (Wei, 2020), an agent-based simulation model (Pedrielli et al., 2020), and a Korea Operational Oceanographic System (KOOS) (Choi et al., 2020). Due to the fast growth of these methods in the field, a comparative analysis of their strengths and weaknesses to disclose their fitness in different voyage scenarios is needed. ...
... Millefiori et al. [3] proposed a novel technique for long-term target state prediction, and the method is based on Stochastic Mean-Reverting Process. Sang et al. [4] developed a three-step closest point of approach (CPA) search method to accurately predict the ship's future trajectory. The AIS data used in this paper were based on the Speed Over Ground (SOG), Course Over Ground (COG), Change of Speed (COS), and rate of turn (ROT) data. ...
The recent emergence of futuristic ships is the result of advances in information and communication technology, big data, and artificial intelligence. They are generally autonomous, which has the potential to significantly improve safety and drastically reduce operating costs. However, the commercialization of Maritime Autonomous Surface Ships requires the development of appropriate technologies, including intelligent navigation systems, which involves the identification of the current maritime traffic conditions and the prediction of future maritime traffic conditions. This study aims to develop an algorithm that predicts future maritime traffic conditions using historical data, with the goal of enhancing the performance of autonomous ships. Using several datasets, we trained and validated an artificial intelligence model using long short-term memory and evaluated the performance by considering several features such as the maritime traffic volume, maritime traffic congestion fluctuation range, fluctuation rate, etc. The algorithm was able to identify features for predicting maritime traffic conditions. The obtained results indicated that the highest performance of the model with a valid loss of 0.0835 was observed under the scenario with all trends and predictions. The maximum values for 3, 6, 12, and 24 days and the congestion of the gate lines around the analysis point showed a significant effect on performance. The results of this study can be used to improve the performance of situation recognition systems in autonomous ships and can be applied to maritime traffic condition recognition technology for coastal ships that navigate more complex sea routes compared to ships navigating the ocean.
... To obtain an accurate CPA, Sang et al. [9] propose a position prediction model in order to extract an accurate shortterm trajectory using AIS data. Additionally, they propose an improvement over the existing CPA calculation methods by adding the change of speed (COS) and rate of turn (ROT), respectively, and take into account all points in the predicted trajectory, instead of only the latest transmitted ones. ...
... For example, the vessel type and speed impact the planning of collision avoidance manoeuvres of vessels and the safe route [5]. CPA, which gives the estimated minimum distance (DCPA) between two vessels the estimated time (TCPA) when they reach this closest point, is an essential factor for navigational safety in collision avoidance [6]. Another factor highly related to the ship's manoeuvrability is UKC, which is defined as the vertical distance between the lowest part of the ship's hull and the seabed [7]. ...
Training in simulator has been used in maritime domain for years due to its cost-effective nature. Different scenarios with varied visibility, traffic density, weather conditions, etc. could be easily set up in the simulators. However, the existing build-in training and assessment package in the simulators is rigid as it does not take into consideration the change in traffic and navigational environment. Human experts are always involved to observe and assess the performance of trainees. An objective and intelligent training and assessment package is proposed to assist the experts in training to ensure objectivity and consistency. To identify the gaps and determine the relevance and the adequacy of the existing build-in assessment in the simulator, online survey has been distributed to the shipping companies and associations. The survey has gathered inputs on the actual shipboard practices when the seafarers are navigating in Singapore waters. This includes different types of vessels, vessel sizes, and external environment conditions such as visibility. The outcome of this analysis is used to form the baseline of a common practice at sea and used in the training and assessment package, which provides consistency in setting the critical training parameters. The training and assessment package reads the data from an advanced navigation research simulator and is able to sense changes and update itself in accordance with user-defined environment. Several assessment modules such as CPA under different traffic density and visibility, minimum distance from other vessels, rate of turn at different speed and loading conditions, will be covered by this training and assessment package.
... To this end, an indicator of an imminent collision is defined in the International Regulations for Preventing Collisions at Sea (COLREG) as a constant compass bearing and decreasing distance between two vessels [3]. Additionally, other operational indicators are used, mainly Distance at Closest Point of Approach (DCPA) and Time to Closest Point of Approach (TCPA) [4][5][6][7] as these are readily available to a decision-maker under normal circumstances. They are calculated based on readings normally provided by navigational equipment, such as Automatic Radar Plotting Aid (ARPA) and Automatic Identification System (AIS) [8], carriage of which is required from most of the merchant fleet, as well as other vessels. ...
Even in the era of automatization maritime safety constantly needs improvements. Regardless of the presence of crew members on board, both manned and autonomous ships should follow clear guidelines (no matter as bridge procedures or algorithms). To date, many safety indicators, especially in collision avoidance have been proposed. One of such parameters commonly used in day-to-day navigation but usually omitted by researchers is Bow Crossing Range (BCR). Therefore, this paper aims to investigate, what are typical, empirical values of BCR during routine operations of merchant ships, as well as investigate what factors impact this indicator and to what extent. To this end, a ten-year big dataset of real maritime traffic obtained from the Automatic Identification System (AIS) was used to provide statistical and spatiotemporal analyses. The results indicate that BCR is strongly related to the type of navigational area (open sea or restricted waters) but not with the dimensions or speed of ships. Among analyzed vessel types, passenger ships were noted as vessels that cross other bows at the closes ranges. Results of this study may be found interesting by fleet managers and developers of Maritime Autonomous Surface Ships (MASS). The former could utilize the results to provide revised operational guidelines for deck officers while the latter - propose an early-detection warning system based on empirical data for prospective MASS.
... Furthermore, the real position [lon t M i , lat t M i ] is replaced with the position [lon t k+1 , lat t k+1 ] at time t k+1 if an AIS message M i occurs in the interval between the kth and (k + 1)th reference times (i.e., t k < t M i < t k+1 ). (2) [28]. ...
Vessel traffic volume and vessel traffic service (VTS) operator workloads are increasing with the expansion of global maritime trade, contributing to marine accidents by causing difficulties in providing timely services. Therefore, it is essential to have sufficient VTS operators considering the vessel traffic volume and near-miss cases. However, no quantitative method for determining the optimal number of workstations, which is necessary for calculating the VTS operator staffing level, has yet been proposed. This paper proposes a new, microscopic approach for calculating the number of workstations from vessel trajectories and voice recording communication data between VTS operators and navigators. The vessel trajectory data are preprocessed to interpolate different intervals. The proposed method consists of three modules: Information services, navigational assistance services, and traffic organization service. The developed model was applied to the Yeosu VTS in Korea. Another workstation should be added to the current workstation based on the proposed method. The results showed that even without annual statistical data, a reasonable VTS operator staffing level could be calculated. The proposed approach helps prevent vessel accidents by providing timely services even if the vessel traffic is congested if VTS operators are deployed to a sufficient number of workstations.
... We add the features above into is associated with ships' motion state [4] in Table A1. Sang et al. [26] and Kim et al. [19] pointed out that AIS equipment installed on different types of ships is of various cost and performance (e.g., fishing boats tend to install AIS equipment with low cost and accuracy), which may lead to the deviation of COG, SOG, ROT and other kinematic information. Considering the situation mentioned above, we calculate ROT , accelerate , speedlng , speedlat , and speed . ...
AIS (Automatic Identification System) is an effective navigation aid system aimed to realize ship monitoring and collision avoidance. Space-based AIS data, which are received by satellites, have become a popular and promising approach for providing ship information around the world. To recognize the types of ships from the massive space-based AIS data, we propose a multi-feature ensemble learning classification model (MFELCM). The method consists of three steps. Firstly, the static and dynamic information of the original data is preprocessed and features are then extracted in order to obtain static feature samples, dynamic feature distribution samples, time-series samples, and time-series feature samples. Secondly, four base classifiers, namely Random Forest, 1D-CNN (one-dimensional convolutional neural network), Bi-GRU (bidirectional gated recurrent unit), and XGBoost (extreme gradient boosting), are trained by the above four types of samples, respectively. Finally, the base classifiers are integrated by another Random Forest, and the final ship classification is outputted. In this paper, we use the global space-based AIS data of passenger ships, cargo ships, fishing boats, and tankers. The model gets a total accuracy of 0.9010 and an F1 score of 0.9019. The experiments prove that MFELCM is better than the base classifiers. In addition, MFELCM can achieve near real-time online classification, which has important applications in ship behavior anomaly detection and maritime supervision.
... Czapiewska and Sadowski compared the performance of the Kalman filtering technique and the linear algorithm as a method of predicting the trajectory of a ship [6]. The linear algorithm is a very simple extrapolation method that calculates the future position based on the observed information, on the assumption that the state information such as the speed, course, and position of the vessel observed in the most recent time period will remain constant in the future [7][8][9][10]. Breda and Passenier compared the three different path predictors through the ship simulation experiments [11]. ...
According to the statistics of maritime accidents, most collision accidents have been caused by human factors. In an encounter situation, the prediction of ship's trajectory is a good way to notice the intention of the other ship. This paper proposes a methodology for predicting the ship's trajectory that can be used for an intelligent collision avoidance algorithm at sea. To improve the prediction performance, the density-based spatial clustering of applications with noise (DBSCAN) has been used to recognize the pattern of the ship trajectory. Since the DBSCAN is a clustering algorithm based on the density of data points, it has limitations in clustering the trajectories with nonlinear curves. Thus, we applied the spectral clustering method that can reflect a similarity between individual trajectories. The similarity measured by the longest common subsequence (LCSS) distance. Based on the clustering results, the prediction model of ship trajectory was developed using the bidirectional long short-term memory (Bi-LSTM). Moreover, the performance of the proposed model was compared with that of the long short-term memory (LSTM) model and the gated recurrent unit (GRU) model. The input data was obtained by preprocessing techniques such as filtering, grouping, and interpolation of the automatic identification system (AIS) data. As a result of the experiment, the prediction accuracy of Bi-LSTM was found to be the highest compared to that of LSTM and GRU.
... However, CQSs must be completely avoided according to International Regulations for Preventing Collisions at Sea (COLREGs) [38], particularly rule 8. Advanced ship domains are uncommon in practice, especially in large data applications due to their computational complexity [39]. On the contrary, Closest Point of Approach (CPA) [40] is a simple technique used to determine near-collision situations through Time to CPA (TCPA) and Distance to CPA (DCPA) parameters that respectively determine when and how close two vessels will be in the near future based on their current position, speed, and course. Due to its simplicity, CPA's potential use is limited to determine situational awareness rather than full risk assessment. ...
Autonomous ships are promoted as the future of the maritime transport industry aiming to overcome conventional vessels in terms of performance, safety and environmental impact. Yet their tangled cyber-physical-social interactions and new emerging properties induce questions regarding their liability and trustworthiness. Digital simulations and sea trials are launched to assure the safety requirements and social expectations are met a priori. This paper presents the design of realistic testbed scenarios from huge historical data through a high-performance computational method to recommend a complete set of navigation scenarios for autonomy tests. The developed approach integrates traffic big data from Automatic Identification System (AIS) with high-resolution digital maps, vessel information registry, and digital nautical charts. All historical vessel-to-ground and vessel-to-vessel interactions are efficiently analyzed through a hierarchical method for collision and grounding conflicts assessment with a 15-minutes prediction horizon. Relative risk is evaluated accurately over full periods of predicted close-quarters situations subject to physical limits and sea-room availability for evasive maneuverers under COLREG rules and traffic separation schemes. Spatial dependencies among multiple conflicts define risky momentary traffic situations modelled through directed graph representation of nested interactions. Their temporal dependencies describe navigation scenarios through dynamic co-behaviors between multiple participating vessels over a period of time. Finally, we analyze negative/positive actions that increase/decrease the complexity. The presented algorithms are computationally very efficient, they scale to several (country*year)s where millions of scenarios are extracted, classified, and scored by their relative risk, complexity, and likelihood for firm post-test conclusions.
... Fishing ships usually are equipped with low-cost, low-fidelity AIS devices having a GPS sensor and gyro compass, meaning that ship course, speed, and position data are not very accurate, and AIS packets are frequently lost. The course and speed data in the AIS packets are measured at a particular moment and as such, they are prone to containing errors [23]. Due to this, the proposed method does not use those data from the AIS packets. ...
Marine resources are valuable assets to be protected from illegal, unreported, and unregulated (IUU) fishing and overfishing. IUU and overfishing detections require the identification of fishing gears for the fishing ships in operation. This paper is concerned with automatically identifying fishing gears from AIS (automatic identification system)-based trajectory data of fishing ships. It proposes a deep learning-based fishing gear-type identification method in which the six fishing gear type groups are identified from AIS-based ship movement data and environmental data. The proposed method conducts preprocessing to handle different lengths of messaging intervals, missing messages, and contaminated messages for the trajectory data. For capturing complicated dynamic patterns in trajectories of fishing gear types, a sliding window-based data slicing method is used to generate the training data set. The proposed method uses a CNN (convolutional neural network)-based deep neural network model which consists of the feature extraction module and the prediction module. The feature extraction module contains two CNN submodules followed by a fully connected network. The prediction module is a fully connected network which suggests a putative fishing gear type for the features extracted by the feature extraction module from input trajectory data. The proposed CNN-based model has been trained and tested with a real trajectory data set of 1380 fishing ships collected over a year. A new performance index, DPI (total performance of the day-wise performance index) is proposed to compare the performance of gear type identification techniques. To compare the performance of the proposed model, SVM (support vector machine)-based models have been also developed. In the experiments, the trained CNN-based model showed 0.963 DPI, while the SVM models showed 0.814 DPI on average for the 24-h window. The high value of the DPI index indicates that the trained model is good at identifying the types of fishing gears.
... Several methods have been proposed for evaluating a measure called the collision risk index, such as DCPA, TCPA and relative bearing change. A widely used collision index is the encounter risk indicator , which is defined with respect to the CPA and TCPA as follows [10]: ...
Excessive information significantly increases the mental burden on operators of critical monitoring services such as maritime and air traffic control. In these fields, vessels and aircraft have sensors that transmit data to a control center. Because of the large volume of collected data, it is infeasible for monitoring stations to display all of the information on monitoring screens that have limited sizes. This paper proposes a method for automatically selecting maritime traffic stream data for display from a large number of candidates in a context-aware manner. Safety is the most important concern in maritime traffic control, and special care must be taken to avoid collisions between vessels at sea. It presents an architecture for an adaptive information visualization system for a maritime traffic control service. The proposed system adaptively determines the information to be displayed based on the safety evaluation scores and expertise of vessel traffic service operators. It also introduces a method for safety context acquisition to assess the risk of collisions between vessels, using parallel and distributed processing of maritime stream data transmitted by sensors on the vessels at sea. It provides an information-filtering, knowledge extraction method based on the work logs of traffic service operators, using a machine learning technique to generate a decision tree. We applied the proposed system architecture to a large dataset collected at a port. Our results indicate that the proposed system can adaptively select traffic information according to port conditions and to ensure safety and efficiency.
... As existing ship domain models apply the ship domain at the current ship position, a collision situation can occur when the distance to the closest point of approach (DCPA) becomes zero, even if the domains of the two ships do not overlap. Therefore, it is necessary to develop a ship domain model that can evaluate the collision situation at the closest point of approach (CPA) ( Yan et al., 2016) during maneuvering while maintaining the current navigational environment. ...
... AIS data contains all the necessary information for mapping the trajectories followed by each vessel and the general maritime traffic of any sea, and for that reason it has been used in several studies. The majority of these studies are focused particularly in traffic analysis and forecasting (Sang et al., 2016), pollution control (Busler et al., 2015), fusion of different maritime data sources (Xu et al., 2015) or identification of vessels' anomalous behaviors (Handayani et al., 2013;Soleimani et al., 2015). Regarding this last topic, there are a set of common abnormal activities involving two vessels that were identified by the domain experts (e.g. ...
Automatic Identification System data has been used in several studies with different directions like traffic forecasting, pollution control or anomalous behavior detection in vessels trajectories. Considering this last subject, the intersection between vessels is often related with abnormal behaviors, but this topic has not been exploited yet. In this paper an approach to assist the domain experts in the task of analyzing these intersections is introduced, based on data processing and visualization. The work was experimented with a proprietary dataset that covers the Portuguese maritime zone, containing an average of 6460 intersections by day. The results show that several intersections were only noticeable with the visualization strategies here proposed.
... Stubberud and Kramer [16] used a neural-extension Kalman filter to dynamically predict a target state online, thus improving the state estimation capability of existing models. Sang et al. [17] built a prediction model by using change of speed (COS), rate of turn (ROT), speed over ground (SOG), and course over ground (COG) to develop the closest point of approaching (CPA) searching method. Nagai and Watanabe [18] proposed a ship-position prediction model for a path following the ship's performance on a curved path. ...
The real-time prediction of ship behavior plays an important role in navigation and intelligent collision avoidance systems. This study developed an online real-time ship behavior prediction model by constructing a bidirectional long short-term memory recurrent neural network (BI-LSTM-RNN) that is suitable for automatic identification system (AIS) date and time sequential characteristics, and for online parameter adjustment. The bidirectional structure enhanced the relevance between historical and future data, thus improving the prediction accuracy. Through the “forget gate” of the long short-term memory (LSTM) unit, the common behavioral patterns were remembered and unique behaviors were forgotten, improving the universality of the model. The BI-LSTM-RNN was trained using 2015 AIS data from Tianjin Port waters. The results indicate that the BI-LSTM-RNN effectively predicted the navigational behaviors of ships. This study contributes significantly to the increased efficiency and safety of sea operations. The proposed method could potentially be applied as the predictive foundation for various intelligent systems, including intelligent collision avoidance, vessel route planning, operational efficiency estimation, and anomaly detection systems.
Accurate ship trajectory prediction (STP) is crucial to realise the early warning of ship collision and ensure maritime safety. Driven by advancements in artificial intelligence technology, deep learning-based STP has become a predominant approach in the research field of ship collision avoidance. This paper, based on a state-of-the-art survey of the existing STP research progress, aims to develop a new bi-directional information fusion-driven prediction model that enables the achievement of more accurate STP results by addressing the drawbacks of the classical methods in the field. In this context, a cascading network model is developed by combining two bi-directional networks in a specific order. It incorporates the Bi-directional Long Short-Term Memory (BiLSTM) and the Bi-directional Gated Recurrent Unit (BiGRU) neural network into a single three-layer, information-enhanced network. It takes advantage of both networks to realise more accurate prediction of ship trajectories. Furthermore, the performance of the proposed model is comprehensively evaluated using Automatic Identification System (AIS) data from three water areas representing traffic scenarios of different safety concerns. The superiority of the proposed model is verified through comparative analysis with twenty other methods, including the state-of-the-art STP in the literature. The finding reveals that the new model is better than all the benchmarked ones, and thus, the new STP solution in this paper makes new contributions to improving autonomous navigation and maritime safety.
Artificial intelligence and Automatic Identification Systems (AIS) play pivotal roles in intelligent maritime navigation for the modern maritime industry. Many artificial intelligence maritime applications based on AIS data have dramatically benefited traditional operations and managements in the field of maritime industry, and also provided state-of-the-art predictive analytics for vessel collisions and route optimization. However, the problem of modeling the interactions of vessels in complex waters still needs to be adequately addressed. In this paper, we focus on using spatiotemporal AIS data to model and forecast multiple vessel trajectories amid dynamic interaction patterns, and we propose a forecast model based on a novel neural network, namely a spatiotemporal multi-graph fusion network (STMGF-Net). The innovative STMGF-Net comprises three crucial modules. First, a Spatiotemporal graph construction module generates interaction graphs of various navigation modes, such as motions, risks, and attributes of vessels, Second, a multi-mode fusion module embeds and fuses the above interaction graphs into STMGF-Net. Finally, squeeze-and-excitation and temporal convolutional networks are introduced as Squeeze-and-excitation temporal convolutional modules to enhance the overall efficiency of the model significantly. Overall, the STMGF-Net can recognize complex spatiotemporal interaction patterns among neighboring vessels so as to capture and integrate these interaction features for achieving high-precision prediction performance in intelligent maritime navigation. In numerical experiments, three water areas of Zhoushan Islands, Yangshan Waters, and Yangtze River Waters are used as training and testing datasets. The results show that STMGF-Net improved prediction errors of average and final distance with increase of 49.637% and 50.622% than classic and state-of-art graph neural networks.
Intelligent maritime transportation is one of the most promising enabling technologies for promoting trade efficiency and releasing the physical labor force. The trajectory prediction method is the foundation to guarantee collision avoidance and route optimization for ship transportation. This article proposes a bidirectional data-driven trajectory prediction method based on Automatic Identification System (AIS) spatio-temporal data to improve the accuracy of ship trajectory prediction and reduce the risk of accidents. Our study constructs an encoder-decoder network driven by a forward and reverse comprehensive historical trajectory and then fuses the characteristics of the sub-network to predict the ship trajectory. The AIS historical trajectory data of US West Coast ships are employed to investigate the feasibility of the proposed method. Compared with the current methods, the proposed approach lessens the prediction error by studying the comprehensive historical trajectory, and 60.28% has reduced the average prediction error. The ocean and port trajectory data are analyzed in maritime transportation before and after COVID-19. The prediction error in the port area is reduced by 95.17% than the data before the epidemic. Our work helps the prediction of maritime ship trajectory, provides valuable services for maritime safety, and performs detailed insights for the analysis of trade conditions in different sea areas before and after the epidemic.
The growing availability of maritime IoT traffic data and continuous expansion of the maritime traffic volume, serving as the driving fuel, propel the latest Artificial Intelligence (AI) studies in the maritime domain. Among the most recent advancements, vessel trajectory prediction is one of the most essential topics for assuring maritime transportation safety, intelligence, and efficiency. This paper presents an up-to-date review of existing approaches, including state-of-the-art deep learning, for vessel trajectory prediction. We provide a detailed explanation of data sources and methodologies used in the vessel trajectory prediction studies, highlight a discussion regarding the auxiliary techniques, complexity analysis, benchmarking, performance evaluation, and performance improvement for vessel trajectory prediction research, and finally summarize the current challenges and future research directions in this field.
In the field of maritime safety, ship encounters are a core component of traffic management and analysis. The calculation of the closest point of approach (CPA) is one of the most important methods for collision risk assessment during an encounter. Due to the factors influencing collision risk in water transportation, the existing CPA index exhibits uncertainties in the awareness of dangerous situations. In this paper, to overcome the shortcoming of the CPA index, which does not consider the vessel dimension, we utilize a polygon to represent the ship position based on related information from automatic identification system (AIS) and propose a method to obtain corrected values of the distance at the CPA (DCPA) and time to the CPA (TCPA) through the geometric relationship of the relative motion between involved vessels. Case analysis is conducted through practical encounter cases in a traffic-intensive area outside a port. The comparison results verify that the proposed method effectively reduces the uncertainties of the original point-based CPA index to better assess the collision risk. The advantage of our correction method is that the dimension-related influencing factors can be integrated without manual intervention, and the improved index retains the objectivity and clear physical meaning of the original CPA index. Therefore, the proposed method has high practical value, especially in busy water areas where a high-risk assessment accuracy is required.
Otomatik Tanımlama Sistemi (AIS), deniz taşımacılığının, çarpışma, yangın ve tehlikeli veya kirletici maddelerin dökülmesi gibi risklere sahip olması nedeniyle günümüzde zorunlu hale gelmiş gözlem ve analiz sistemidir. Literatürde, bu tehlikeli durumların önceden tespitinin yapılıp, gemilerin kontrollü ve güvenli seyahatlerini gerçekleştirmeleri için AIS verilerinin kullanıldığı temel matematiksel modellerin, istatistiksel modellerin ve makine öğrenmesi algoritmaların uygulamalarını görebilmekteyiz. Bu çalışmada AIS verileri zaman serileri bakış açısıyla ele alınmış ve geleneksel rota tahminleme modeli yanında; Bütünleşik Otoregresif Hareketli Ortalama, Çok Katmanlı Algılayıcı (ÇKA) ve Kendini Tekrarlayan Derin Sinir Ağları (KT-DSA) ile farklı modeller oluşturularak doğruluk karşılaştırmaları yapılmıştır. Ayrıca ÇKA ve KT-DSA modellerinde, öznitelik seçim tekniklerinden yararlanılarak nitelikler ağırlıklandırılmış ve bu iyileştirilmelerle yeni algoritmalar önerilmiştir. Öznitelik seçimlerinden Relief, Pearson’nun Korelasyonu, Kazanım Oranı ve Bilgi Kazanımı (BK) metotları kullanılmış ve verdikleri rota ve çarpışma tahminlemelerinin doğrulukları karşılaştırılmıştır. Bu doğruluk testlerinde kullanılmak üzere veri seti olarak belirli zamanlara ait Çanakkale Boğazı ve Marmara Denizi AIS verilerinden faydalanılmıştır. Sonuçlara bakıldığında Çanakkale Boğazı’ndaki gemilerin doğrusal bir hareket yapısına sahip olmasından dolayı tüm yaklaşımların birbirine yakın ve yüksek doğruluklara sahip olduğu gözlemlenirken, düzensiz yapısından dolayı Marmara Denizi’nde en iyi sonucu veren yaklaşımın BK ile iyileştirilmiş KT-DSA olduğu sonucuna varılmıştır.
Maritime transport faces new safety-related challenges resulting from constantly increasing traffic density, along with increasing dimensions of ships. Consequently, the number of new concepts related to Decision Support Systems (DSSs) supporting safe shipborne operations in the presence of reduced ship manning is rapidly growing, both in academia and industry. However, there is a lack of a systematic description of the state-of-the-art in this field. Moreover, there is no comprehensive overview of the level of technology readiness of proposed concepts. Therefore, this paper presents an analysis aiming at (1) increasing the understanding of the structure and contents of the academic field concerned with this topic; (2) determining and mapping scientific networks in this domain; (3) analyzing and visualizing Technology Readiness Level (TRL) of analyzed systems. Bibliometric methods are utilized to depict the domain of onboard DSSs for operations focused on safety ensurance and accident prevention. The scientific literature is reviewed in a systematic way using a comparative analysis of existing tools. The results indicate that there are relatively many developments in selected DSS categories, such as collision avoidance and ship routing. However, even in these categories some issues and gaps still remain, so further improvements are needed. The analysis indicates a relatively low level of technology readiness of tools and concepts presented in academic literature. This signifies a need to move beyond the conceptual stages toward demonstration and validation in realistic, operating environments.
Ferries are usually used for transporting passengers and vehicles among docks, and any deviation of the course can lead to serious consequences. Therefore, transportation ferries must be watched closely by local maritime administrators, which involves much manpower. With the use of historical data, this article proposes an intelligent method of integrating artificial potential field with Bayesian Network to trigger deviation warnings for a ferry based on its trajectory, speed and course. More specifically, a repulsive potential field-based model is first established to capture a customary waterway of ferries. Subsequently, a method based on non-linear optimisation is introduced to train the coefficients of the proposed repulsive potential field. The deviation of a ferry from the customary route can then be quantified by the potential field. Bayesian Network is further introduced to trigger deviation warnings in accordance with the distribution of deviation values, speeds and courses. Finally, the proposed approach is validated by the historical data of a chosen ferry on a specific route. The testing results show that the approach is capable of providing deviation warnings for ferries accurately and can offer a practical solution for maritime supervision.
The paper provides a description of a method of drafting route plan templates on the basis of AIS (automatic identification system) historical data. The first section features a brief background on the problem of drafting route plan templates in the light of international regulations. The main section contains a description of the methods and tools used for processing AIS data into a GRID reference system: ship traffic intensity, average COG (course over ground) and average SOG (speed over ground) as well as route plan templates. The final section includes a presentation of the research method and an analysis of the results, conducted on the basis of maps with charted paths of drafted route plan templates. The summary constitutes a synthesis of general conclusions, the advantages and disadvantages of the solution as well as areas for further research to enhance the solution.
The growing volume of maritime traffic is proving a hindrance to navigational safety. Researchers have sought to improve the safety of maritime transportation by conducting statistical analysis on historical collision data in order to identify the causes of maritime collisions. However, this approach is hindered by the limited number of incidents that can be collected in a given area over a given period of time. Automatic Identification System (AIS) has made available enormous quantities of maritime traffic data. Trajectory data are collected through the electronic exchange of navigational data among ships and terrestrial and satellite base stations. Due to a massive AIS data of recording ship movement, such data provide great opportunity to discover maritime traffic knowledge of movement behavior analysis, route estimation, and the detection of anomalous behaviors. Our objective in this paper was to identify potential between-ship traffic conflicts through the discovery of AIS data. Traffic conflict refers to trajectories that could lead to a collision if the ships do not take any evasive action. In other words, conflicting trajectories can be treated as a near-collision cases for analysis. The prevention of collisions requires an efficient method by which to extract conflicting trajectories from a massive collection of AIS data. To this end, we developed a framework CCT Discovery that allows the automated identification of clusters of conflicting trajectories (CCTs) from AIS data without supervision. Experiments based on real-world data demonstrate the efficacy of the proposed framework in terms of accuracy and efficiency. For improvement in the navigational traffic safety, the discovered data of conflict trajectory can contribute to numerous applications, such as collision situation awareness and prediction, anti-collision behaviors modeling and recommendation, and conflict area analysis for maritime traffic flow management.
Due to high density of vessel traffic, busy waterways are water areas with high potential for collisions. The application of AIS makes it possible to investigate accurate and actual behavior of collision-involved ships, and benefits vessel traffic management and waterways design for these areas. As a case study, the authors focus on a Traffic Separation Scheme (TSS) off Rotterdam Port in Europe, and using AIS data, statistical analysis is made for collision involved ships. In order to identify the correlation of CPA, which is a key indicator for collision avoidance, with ship's size, speed, and course, linear regression models are developed. To assess risks, a dynamic method based on SAMSON is presented.
The actions to be taken by navigators to prevent collisions with other vessels are specified in the Interna tional Regulations for Preventing Collisions at Sea (COLREGS 72). Concrete limit values at which the navigator has to order the actions specified are not given in the rules. Today collision avoidance actions by intuition or experience alone are not advisable any longer, with all due deference to “ good seamanship”. p]Many technical aids are available on board ships which assist navigators in their different tasks. Neverthe less, objective criteria for the assessment of encounter situations are still missing. Therefore, a common risk model has been created which is based on COLREGS and consists of four risk levels. They were derived from the actions specified in the relevant steering and sailing rules (Part B of COLREGS). The actual value of CPA, actual distance between the ships involved in an encounter situation and identified limit values are needed for application of the risk model. A risk level will be identified by comparison of actual parameters with limit values.
The trajectory of the inland waterway ship is important and useful in analysing the features of the ship behaviour and simulating traffic flows. In the proposed research, a method is designed to restore the trajectory of an inland waterway ship based on the Automatic Identification System (AIS) data. Firstly, three rules are developed to identify and remove the inaccurate data, based on the reception range of the received AIS data and the manoeuvring characteristics of the inland waterway ship. Secondly, the method of restoring the full trajectory incorporating navigational features of the inland waterway ship is proposed to model the ship trajectory. The trajectory is characterised by three types (line, curve and arc) and five steps (line, curve, arc, curve and line) during the turning section. In order to validate the proposed method, the AIS data of two inland waterway ships collected from three AIS-base-stations is selected for the analysis, all inaccurate AIS data is identified and removed by the use of three cleansing rules. The results show that the three developed rules can effectively identify the inaccurate AIS data. The AIS data collected by an AIS-shipboard-unit is then used to: (1) restore the ship trajectory, and (2) validate the proposed method by comparing the reconstituted trajectories with the actual trajectory. This actual trajectory is determined from intermediate higher frequency Global Positioning System (GPS) data and collected from the AIS-shipboard-unit. The residual errors are calculated as the differences between the estimated latitude values of the restored trajectory functions and the real latitude values of the GPS data. Three alternative methods of trajectory restoring are also evaluated. The results show that the proposed method can be used to restore the full trajectory in an effective manner by using AIS data.
This paper proposes a real-time collision avoidance algorithm for midair unmanned aerial vehicles (UAVs). The algorithm is developed based on the geometry of the closest-point-of-approach (CPA) and a collision detection/resolution scheme. To deal with multiple aircraft, the avoidance velocity of one's own aircraft is expressed in an explicit form, where the avoidance velocity is a component of the safety boundary. The safety boundary is projected on the domain of the flight path angles, and sampling points are chosen along the boundary. The domain of the flight path angles provides directions along which the aircraft can move without collisions, which can reduce the computational load for real-time applications. A collision avoidance solution is obtained by examining possible collision cases involving intruders. The singularity of the geometric approach is also analyzed, and an additional boundary for the singularity is adopted to prevent unexpected maneuvers. The validity of the algorithm is demonstrated through numerical simulations for the non-cooperative and multiple aircraft avoidance problems.
This paper aims at evaluating the collision risk between the encountering vessels under time- -variant CPA situations and then assessing the maritime traffic characteristics. Radar and AIS data are collected from Mokpo VTS in Korea. All crossing vessels that are navigating within CPA 1 miles of Mokpo-Gu waterway are analyzed. The maritime traffic characteristics is analyzed by surveying the distribution of CPA as a function of TCPA. To make it clear, the traffic operating rate in the Mokpo waterway is also computed. The averages of CPA and TCPA were observed until the encountered vessels pass safety each other after they come in a certain ship domain. As a consequence, the distribution of CPA as a function of TCPA gives a useful information to evaluate the maritime traffic safety.
The WAVE (IEEE 1609) standard and vehicular technology create a new opportunity for telematics service. Safety is one of the top issues of telematics service. In this paper, we propose a proactive safety method that can alert drivers before the accident occurs using WAVE. An algorithm named Early Collision Warning Algorithm (ECWA) was proposed in this paper. In ECWA, vehicles broadcast Relationship Information (RI) to neighboring vehicles periodically. Each vehicle calculates whether potential collisions may happen or not upon receiving RI messages. After calculation, ECWA sends warning messages to drivers if the collision will occur. ECWA allows drivers to set the warning level and warning distance by themselves. In our simulation, not only vehicles's collisions at an intersection were simulated but also the GPS error range was considered in our design. The results show that ECWA has good performance and can always alert drivers suitably if the GPS error range was small. Even though the GPS error range is large, ECWA also can enhance the hit rate of warning messages. Copyright © 2011 John Wiley & Sons, Ltd.
A study was conducted to demonstrate reactive collision avoidance of unmanned aerial vehicles (UAV) using a single vision sensor. The study proposed a reactive collision-avoidance algorithm based on the closest point of approach (CPA) and the geometry of the intruder obtained by a single vision sensor. The main contribution was to develop a collision-avoidance algorithm for a UAV using a single vision sensor, which avoided a collision with an intruder while overcoming the loss-of-depth problem of the single vision sensor. The characteristics of the CPA with respect to the intruder's size were analyzed by using the geometry of the intruder obtained by a single vision sensor. A direction condition that is safe and robust to the motion of the intruder was proposed and a time condition to regulate the side effect of the loss-of-depth problem was developed.
Traffic Collision Avoidance System (TCAS) is designed to enhance safety in aircraft operations, by reducing the incidences of mid-air collision between aircraft. The current version of TCAS provides only vertical resolution advisory to the pilots, if an aircraft's collision with another is predicted to be imminent, while efforts to include horizontal resolution advisory have been made, as well. This paper introduces a collision resolution algorithm, which includes both vertical and horizontal avoidance maneuvers of aircraft. Also, the paper compares between the performance of the proposed algorithm and that of algorithms with only vertical or horizontal avoidance maneuver of aircraft.
The use of a numerical hill climbing technique in the solution of two chemical engineering problems is described. The first problem is concerned with designing a chemical plant for minimum cost per unit yield. The second problem deals with a method of obtaining the best temperature profile in a chemical reaction vessel by assuming the vessel to be divided into a number of stirred tanks.A brief review is given of methods of finding maxima or minima of functions when the variables are not completely independent but subject to constraints.RésuméCet article traite de l'application d'une technique numérique procédant par paliers pour la résolution de deux problèmes de Génie Chimique. Le premier problème concerne le calcul d'une usine chimique pour un prix de revient minimum par unité de rendement. Le second problème concerne l'optimisation du profil de température dans un réacteur en supposant le récipient divisé en un certain nombre de réacteurs à agitation.L'auteur passe rapidement en revue les méthodes permettant de trouver les maxima ou minima des fonctions quand les variables ne sont pas entièrement indépendantes.ZusammenfassungDie Anwendung einer numerischen Anstiegsmethode zur Lösung zweier chemischtechnologischer Probleme wird beschrieben. Das erste Problem betrifft die Auslegung einer chemischen Anlage für minimale Kosten pro Produktionseinheit. Das zweite Problem behandelt eine Methode zur Ermittlung des besten Temperaturverlaufs in einem Reaktionsgefäss; dabei wird angenommen, dass das Gefäss in eine Anzahl Rührkessel aufgeteilt werden muss.Es wird ein kurzer Überblick über Methoden zum Auffinden der Maxima oder Minima von Funktionen gegeben, bei denen die Variablen nicht völlig unabhängig, sondern Einschränkungen unterworfen sind.
The problem of errors in radar plotting were considered by Capt. H. Topley (11, 167) and Capt. F. J. Wylie (12, 198), and it was shown that the error in the estimated distance of the C.P.A. depends upon mean range and range change in plotting interval. I want to introduce the term rate of error in the estimated distance of C.P.A., in the same way that Topley shows the percentage error in the estimated speed.
An increase in the likelihood of navigational collisions in port waters has put focus on the collision avoidance process in port traffic safety. The most widely used on-board collision-avoidance system is the automatic radar plotting aid which is a passive warning system that triggers an alert based on the pilot’s pre-defined indicators of distance and time proximities at the closest point of approaches in encounters with nearby vessels. To better help pilot in decision making in close quarter situations, collision risk should be considered as a continuous monotonic function of the proximities and risk perception should be considered probabilistically. This paper derives an ordered probit regression model to study perceived collision risks. To illustrate the procedure, the risks perceived by Singapore port pilots were obtained to calibrate the regression model. The results demonstrate that a framework based on the probabilistic risk assessment model can be used to give a better understanding of collision risk and to define a more appropriate level of evasive actions.
The growing use of computers for mechanized inventory control and production planning has brought with it the need for explicit forecasts of sales and usage for individual products and materials. These forecasts must be made on a routine basis for thousands of products, so that they must be made quickly, and, both in terms of computing time and information storage, cheaply; they should be responsive to changing conditions. The paper presents a method of forecasting sales which has these desirable characteristics, and which in terms of ability to forecast compares favorably with other, more traditional methods. Several models of the exponential forecasting system are presented, along with several examples of application.
The paper provides a systematic development of the forecasting expressions for exponential weighted moving averages. Methods for series with no trend, or additive or multiplicative trend are examined. Similarly, the methods cover non-seasonal, and seasonal series with additive or multiplicative error structures. The paper is a reprinted version of the 1957 report to the Office of Naval Research (ONR 52) and is being published here to provide greater accessibility. (C) 2004 Published by Elsevier B.V. on behalf of International Institute of Forecasters.
Movable Type Scripts: Calculate Distance, Bearing and more between Latitude/Longitude Points
- C Veness